AI-enhanced discharge performance in hexagonal shell and finned tube latent heat storage using combined longitudinal smooth and Y-shaped fins
Khalil Hajlaoui, Hakim S. Sultan Aljibori, Hayder I. Mohammed, Wahiba Yaïci, Mohammad Edalatifar, Nashmi H. Alrasheedi, Mohammad Ghalambaz, Pouyan Talebizadehsardari
Abstract
The aim of this study is to enhance the discharge performance of shell and finned-tube heat exchanger using hexagon shell. Different fins arrangement including combinations of longitudinal straight and Y-shaped fins in uniform and non-uniform forms are assessed. An artificial intelligence approach based on artificial intelligence networks is used to learn the overall state of solution and behavior of the discharge rate respect to the control parameters and further enhance the design. The innovation consists of the methodical investigation of Y-shaped fin geometries to concurrently improve conductivity and mitigate convection, in contrast to traditional straight-fin configurations. The findings indicate that Y-shaped fins with 0.5L stems at 45° angles exhibit enhanced performance, diminishing solidification time by 95.3% and augmenting heat recovery rates by 2,277% (to 302.89 W) in comparison to finless systems. The AI results further confirm a fin with a stem in the range of 0.3L-0.5L and angle of 45° could provide the best discharging performance. The principal findings indicate that the 0.5L-45° arrangement attains excellent thermal homogeneity (inter-branch gradients < 5 K) and minimum convection disruption (72% flow obstruction), whereas wider angles or longer stems diminish efficiency due to convective bypass and thermal shadowing.